1. NCCU Academic Hub
  2. 學術產出
  3. 商學院
  4. 學位論文
  5. Item

學術產出-學位論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 運用文字探勘技術建置知識本體之研究 -以財經文件為例
The study of constructing ontology with text mining techniques－Take the macroeconomic analysis report for an instance
作者 蘇晏譁
Su, Yan Hua
貢獻者 劉文卿
Liou, Wen Ching
蘇晏譁
Su, Yan Hua
關鍵詞 文字探勘
知識本體
Text mining
Ontology
日期 2009
上傳時間 9-五月-2016 15:17:57 (UTC+8)
摘要 　　隨著理財觀念日漸普及，個人與企業對於財經相關資訊的需求也與日俱增。然而，各式各樣隱含有用資訊的財經相關文件雖然越來越容易取得，但多是以文字的方式呈現，無固定格式，較不易整理。如何協助使用者自大量財經文件中尋找和擷取出適當的資訊，已經成為財經相關應用領域的重要研究議題。
     　　在目前眾多知識挖掘相關方法中，文字探勘（text mining）即是以文件內容為主要分析對象，目的在於自非結構或半結構化的文件中萃取出有意義的知識。為此，若有一個良好的機制能將文字探勘所挖掘的知識加以彙整併保存，便可使財經文件內所隱藏的知識進一步的被應用在相關領域上(如決策支援、資訊檢索、知識管理，而這也成為提昇競爭力的重要利基。
     　　本研究針對財經領域相關文件（如財經新聞、投顧之研究報告…等）進行分析，結合文字探勘知識挖掘的能力與知識本體的概念，運用文字探勘中重要演算法－關聯分析挖掘財經文件中隱含的關鍵資訊，提出一套藉由關聯分析所得之關聯規則建立知識本體的新方法。此方法有以下幾點特色：(1)建構一「財經標的模型」，定義財經文件內容之基本架構(2)將文字探勘挖掘之知識以知識本體的方式呈現(3)自動化的建構知識本體。
　With the concept of financial management popularizing, Personal and corporations are increasing the financial information demands. However, implicit in all kinds of useful information relevant macroeconomic documents readily available, but most text has no fixed format and difficult to collate. To support users from a large number of macroeconomic documents to find and retrieve the appropriate information has become important research topic in financial-related applications.
     　In many Knowledge Mining Approaches, Text mining is based on analyzing the content of the documents; it purpose to extract the meaningful knowledge from Unstructured or Semi-structured Documents. If there is a good mechanism to keep the accumulation of text mining knowledge exploration, the macroeconomic documents will enable to effective application of tacit knowledge in Decision Support, Information Retrieval, Knowledge Management and other related fields, it is the foundation of enhancing competitiveness.
     　This study aims to analyzing the macroeconomic documents such as the financial and economic news, the research report of investment consular… and so on, Combined with Text Mining knowledge mining ability and concept of Ontology, by one of the important algorithms to text mining－Association Analysis, discovered latent key information in macroeconomic documents, apply a new method of Association Rules for building Ontology. The method has the following characteristics：(1) Constructed 「Target Model」on structure framework to give a definition for the macroeconomic documents (2) To display the knowledge form text mining by Ontology approaches (3) Constructing Ontology automatically。
參考文獻 1.Agrawal, R.、Srikant, R. (1994). Fast Algorithms for Mining Association Rules. the 20th VLDB Conference, santiago.
     2.Aurora, P.P.、Rafael, B.L.、José, R.S. (2007). Topic discovery based on text mining techniques. Information Processing & Management, 43(3), 752-768.
     3.Borst, W.N. (1997). Construction of Engineering Ontologies for Knowledge Sharing and Reuse. PhD Thesis, University of Twente, Enschede, The Netherlands.
     4.Delen, D.、Crossland, M.D. (2008). Seeding the survey and analysis of research literature with text mining. Expert Systems with Application, 34,1707-1720.
     5.Dörre, J.、Gerstl, P.、Seiffert, R. (1999). Text Mining:Finding Nuggets in Mountains of Textual Data. Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 398-401.
     6.Guarno, N. (1995). Ontology, conceptual analysis and knowledge representation. International Journal of Human-Computer Studies,43,625-640.
     7.Guarino, N. (1998). Formal Ontology and Information Systems. Formal Ontology in Information Systems Proceeding of the 1st International Conference, 3-15.
     8.Feldman, R.、Hirsh, H. (1996). Mining associations in text in the presence of background knowledge. Knowledge Discovery and Data Miningn Conference,Portland.
     9.Feldman, R.、Sanger, J. (2006). The Text Mining Handbook. Cambridge University Press.
     10.Jiang, G.、Ogasawara, K.、Endoh, A.、Sakurai, T. (2003). Context-based Ontology Building Support in Clinical Domains using Formal Concept Analysis. Journal of Medical Informatics, 71(1), 71-81.
     11.Lo, S. (2008). Web service quality control based on text mining using support vector machine. Expert Systems with Application, 34, 603-610.
     12.Simoudis, E. (1996). Reality check for data mining. IEEE Expert, October, 26-33.
     13.Studer, R.、Benjamins, V. R.、Fensel, D.(1998). Knowledge engeering: principles and methods. Data and knowledge engineering, vol 25,161-197.
     14.Tzeng ,J.S.、Liou, W.C.、Sun, C.M. (2009). Constructing A Lexical Semantic Network Based On A Domain Dictionary. KANSEI Engineering International, vol 7, 47-53.
     15.William, S.、Austin, T. (1999). Ontologies. IEEE Intelligent sysytems,Jan/Feb, 18-19.
     16.Yang, H.C.、Lee, C.H. (2004). A text mining approach on automatic generation of web directories and hierarchies. Expert Systems with Applications, 27, 645-663.
     17.余治平(2002)。哲學的鎖鑰 : 源於本體論的形上之思。台北：五南圖書出版公司。
     18.李維平、吳澤民、王美淳(2007)。利用共生詞彙特性發展一個二階段文件群集法。科學與工程技術期刊，3，10-25。
     19.阮明淑、溫達茂(2002)。ontology應用於知識組織之初探。佛教圖書館館訊，32，6-17。
     20.張婷芳(2007)。結合本體論與詞彙鏈群聚之文件分群研究。國立臺灣科技大學資訊管理學系碩士論文，未出版，台北市。
     21.許中川、陳景揆(2001)。探勘中文新聞文件。資訊管理學報，l7，103-122。
     22.陳彥勳(2006)。使用WWW資源協助知識本體整合。國立成功大學資訊管理學系碩士論文，未出版，台南市。
     23.蕭淑玲、周世俊(2003)。運用文件探勘於語料庫之辦公室服務代理人。電子商務學報，5，61-86。
     24.鍾任明、李維平、吳澤民(2007)，運用文字探勘於日內股價漲跌趨勢預測之研究。中華管理評論國際學報，10，1-30。
描述 碩士
國立政治大學
資訊管理學系
96356003
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0096356003
資料類型 thesis
dc.contributor.advisor 劉文卿zh_TW
dc.contributor.advisor Liou, Wen Chingen_US
dc.contributor.author (作者) 蘇晏譁zh_TW
dc.contributor.author (作者) Su, Yan Huaen_US
dc.creator (作者) 蘇晏譁zh_TW
dc.creator (作者) Su, Yan Huaen_US
dc.date (日期) 2009en_US
dc.date.accessioned 9-五月-2016 15:17:57 (UTC+8)-
dc.date.available 9-五月-2016 15:17:57 (UTC+8)-
dc.date.issued (上傳時間) 9-五月-2016 15:17:57 (UTC+8)-
dc.identifier (其他 識別碼) G0096356003en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/95157-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊管理學系zh_TW
dc.description (描述) 96356003zh_TW
dc.description.abstract (摘要) 　　隨著理財觀念日漸普及，個人與企業對於財經相關資訊的需求也與日俱增。然而，各式各樣隱含有用資訊的財經相關文件雖然越來越容易取得，但多是以文字的方式呈現，無固定格式，較不易整理。如何協助使用者自大量財經文件中尋找和擷取出適當的資訊，已經成為財經相關應用領域的重要研究議題。
     　　在目前眾多知識挖掘相關方法中，文字探勘（text mining）即是以文件內容為主要分析對象，目的在於自非結構或半結構化的文件中萃取出有意義的知識。為此，若有一個良好的機制能將文字探勘所挖掘的知識加以彙整併保存，便可使財經文件內所隱藏的知識進一步的被應用在相關領域上(如決策支援、資訊檢索、知識管理，而這也成為提昇競爭力的重要利基。
     　　本研究針對財經領域相關文件（如財經新聞、投顧之研究報告…等）進行分析，結合文字探勘知識挖掘的能力與知識本體的概念，運用文字探勘中重要演算法－關聯分析挖掘財經文件中隱含的關鍵資訊，提出一套藉由關聯分析所得之關聯規則建立知識本體的新方法。此方法有以下幾點特色：(1)建構一「財經標的模型」，定義財經文件內容之基本架構(2)將文字探勘挖掘之知識以知識本體的方式呈現(3)自動化的建構知識本體。		zh_TW
dc.description.abstract (摘要) 　With the concept of financial management popularizing, Personal and corporations are increasing the financial information demands. However, implicit in all kinds of useful information relevant macroeconomic documents readily available, but most text has no fixed format and difficult to collate. To support users from a large number of macroeconomic documents to find and retrieve the appropriate information has become important research topic in financial-related applications.
     　In many Knowledge Mining Approaches, Text mining is based on analyzing the content of the documents; it purpose to extract the meaningful knowledge from Unstructured or Semi-structured Documents. If there is a good mechanism to keep the accumulation of text mining knowledge exploration, the macroeconomic documents will enable to effective application of tacit knowledge in Decision Support, Information Retrieval, Knowledge Management and other related fields, it is the foundation of enhancing competitiveness.
     　This study aims to analyzing the macroeconomic documents such as the financial and economic news, the research report of investment consular… and so on, Combined with Text Mining knowledge mining ability and concept of Ontology, by one of the important algorithms to text mining－Association Analysis, discovered latent key information in macroeconomic documents, apply a new method of Association Rules for building Ontology. The method has the following characteristics：(1) Constructed 「Target Model」on structure framework to give a definition for the macroeconomic documents (2) To display the knowledge form text mining by Ontology approaches (3) Constructing Ontology automatically。		en_US
dc.description.tableofcontents 第一章、研究動機與目的 5
     第二章、文獻探討 8
     2.1 知識本體 8
     2.2 文字探勘 10
     2.3 中文斷詞系統 11
     第三章、研究方法 13
     3.1 財經標的模型 13
     3.2 資料前置處理階段 16
     3.3 知識萃取階段 17
     3.3.1關聯分析 18
     3.3.2 知識本體建構 20
     第四章、實驗設計與結果 22
     4.1 實驗設計 22
     4.2 實驗結果與分析 22
     第五章、結論與建議 29
     參考文獻 32
     附錄一 35		zh_TW
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0096356003en_US
dc.subject (關鍵詞) 文字探勘zh_TW
dc.subject (關鍵詞) 知識本體zh_TW
dc.subject (關鍵詞) Text miningen_US
dc.subject (關鍵詞) Ontologyen_US
dc.title (題名) 運用文字探勘技術建置知識本體之研究 -以財經文件為例zh_TW
dc.title (題名) The study of constructing ontology with text mining techniques－Take the macroeconomic analysis report for an instanceen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) 1.Agrawal, R.、Srikant, R. (1994). Fast Algorithms for Mining Association Rules. the 20th VLDB Conference, santiago.
     2.Aurora, P.P.、Rafael, B.L.、José, R.S. (2007). Topic discovery based on text mining techniques. Information Processing & Management, 43(3), 752-768.
     3.Borst, W.N. (1997). Construction of Engineering Ontologies for Knowledge Sharing and Reuse. PhD Thesis, University of Twente, Enschede, The Netherlands.
     4.Delen, D.、Crossland, M.D. (2008). Seeding the survey and analysis of research literature with text mining. Expert Systems with Application, 34,1707-1720.
     5.Dörre, J.、Gerstl, P.、Seiffert, R. (1999). Text Mining:Finding Nuggets in Mountains of Textual Data. Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 398-401.
     6.Guarno, N. (1995). Ontology, conceptual analysis and knowledge representation. International Journal of Human-Computer Studies,43,625-640.
     7.Guarino, N. (1998). Formal Ontology and Information Systems. Formal Ontology in Information Systems Proceeding of the 1st International Conference, 3-15.
     8.Feldman, R.、Hirsh, H. (1996). Mining associations in text in the presence of background knowledge. Knowledge Discovery and Data Miningn Conference,Portland.
     9.Feldman, R.、Sanger, J. (2006). The Text Mining Handbook. Cambridge University Press.
     10.Jiang, G.、Ogasawara, K.、Endoh, A.、Sakurai, T. (2003). Context-based Ontology Building Support in Clinical Domains using Formal Concept Analysis. Journal of Medical Informatics, 71(1), 71-81.
     11.Lo, S. (2008). Web service quality control based on text mining using support vector machine. Expert Systems with Application, 34, 603-610.
     12.Simoudis, E. (1996). Reality check for data mining. IEEE Expert, October, 26-33.
     13.Studer, R.、Benjamins, V. R.、Fensel, D.(1998). Knowledge engeering: principles and methods. Data and knowledge engineering, vol 25,161-197.
     14.Tzeng ,J.S.、Liou, W.C.、Sun, C.M. (2009). Constructing A Lexical Semantic Network Based On A Domain Dictionary. KANSEI Engineering International, vol 7, 47-53.
     15.William, S.、Austin, T. (1999). Ontologies. IEEE Intelligent sysytems,Jan/Feb, 18-19.
     16.Yang, H.C.、Lee, C.H. (2004). A text mining approach on automatic generation of web directories and hierarchies. Expert Systems with Applications, 27, 645-663.
     17.余治平(2002)。哲學的鎖鑰 : 源於本體論的形上之思。台北：五南圖書出版公司。
     18.李維平、吳澤民、王美淳(2007)。利用共生詞彙特性發展一個二階段文件群集法。科學與工程技術期刊，3，10-25。
     19.阮明淑、溫達茂(2002)。ontology應用於知識組織之初探。佛教圖書館館訊，32，6-17。
     20.張婷芳(2007)。結合本體論與詞彙鏈群聚之文件分群研究。國立臺灣科技大學資訊管理學系碩士論文，未出版，台北市。
     21.許中川、陳景揆(2001)。探勘中文新聞文件。資訊管理學報，l7，103-122。
     22.陳彥勳(2006)。使用WWW資源協助知識本體整合。國立成功大學資訊管理學系碩士論文，未出版，台南市。
     23.蕭淑玲、周世俊(2003)。運用文件探勘於語料庫之辦公室服務代理人。電子商務學報，5，61-86。
     24.鍾任明、李維平、吳澤民(2007)，運用文字探勘於日內股價漲跌趨勢預測之研究。中華管理評論國際學報，10，1-30。		zh_TW